From b2f7314d314bebc899de9194064440c379b0c198 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fabiano=20Fid=C3=AAncio?= <ffidencio@nvidia.com>
Date: Wed, 24 Jun 2026 18:52:25 +0200
Subject: [PATCH] tests: harden sandbox sizing manifests for k8s cpu workloads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Route runtime-rs tests to dedicated manifests/templates and ensure the
CPU allocation workloads always carry explicit memory limits, avoiding
Dragonball sandbox startup failures from InvalidMemorySize(0).

Signed-off-by: Fabiano Fidêncio <ffidencio@nvidia.com>
Assisted-by: Cursor <cursoragent@cursor.com>
---
 .../kubernetes/k8s-sandbox-vcpus-allocation.bats       | 10 ++++++++--
 .../runtimeclass_workloads/pod-cpu-defaults.yaml       |  5 +++++
 .../kubernetes/runtimeclass_workloads/pod-cpu.yaml     |  2 ++
 .../runtimeclass_workloads/pod-number-cpu.yaml         |  2 ++
 .../pod-sandbox-vcpus-allocation.yaml                  |  5 +++++
 tests/integration/kubernetes/tests_common.sh           |  2 +-
 6 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/tests/integration/kubernetes/k8s-sandbox-vcpus-allocation.bats b/tests/integration/kubernetes/k8s-sandbox-vcpus-allocation.bats
index e24f88b4a8..47118ee1c1 100644
--- a/tests/integration/kubernetes/k8s-sandbox-vcpus-allocation.bats
+++ b/tests/integration/kubernetes/k8s-sandbox-vcpus-allocation.bats
@@ -31,8 +31,14 @@ setup() {
 	# Create the pods
 	kubectl create -f "${yaml_file}"
 
-	# Wait for completion
-	kubectl wait --for=jsonpath='{.status.phase}'=Succeeded --timeout=$timeout pod --all
+	# Wait for each test container to terminate successfully. Using container
+	# termination state is more robust than pod phase checks, which can lag.
+	for pod in "${pods[@]}"; do
+		kubectl wait \
+			--for=jsonpath='{.status.containerStatuses[0].state.terminated.reason}'=Completed \
+			--timeout=$timeout \
+			"pod/${pod}"
+	done
 
 	# Check the pods
 	for i in {0..2}; do
diff --git a/tests/integration/kubernetes/runtimeclass_workloads/pod-cpu-defaults.yaml b/tests/integration/kubernetes/runtimeclass_workloads/pod-cpu-defaults.yaml
index 7973ea1bbc..ee227af14c 100644
--- a/tests/integration/kubernetes/runtimeclass_workloads/pod-cpu-defaults.yaml
+++ b/tests/integration/kubernetes/runtimeclass_workloads/pod-cpu-defaults.yaml
@@ -13,3 +13,8 @@ spec:
   - name: default-cpu-demo-ctr
     image: quay.io/prometheus/busybox:latest
     command: ["tail", "-f", "/dev/null"]
+    resources:
+      limits:
+        memory: "128Mi"
+      requests:
+        memory: "64Mi"
diff --git a/tests/integration/kubernetes/runtimeclass_workloads/pod-cpu.yaml b/tests/integration/kubernetes/runtimeclass_workloads/pod-cpu.yaml
index 976bf44236..0ca927ecd2 100644
--- a/tests/integration/kubernetes/runtimeclass_workloads/pod-cpu.yaml
+++ b/tests/integration/kubernetes/runtimeclass_workloads/pod-cpu.yaml
@@ -18,5 +18,7 @@ spec:
     resources:
       limits:
         cpu: "1"
+        memory: "128Mi"
       requests:
         cpu: "500m"
+        memory: "64Mi"
diff --git a/tests/integration/kubernetes/runtimeclass_workloads/pod-number-cpu.yaml b/tests/integration/kubernetes/runtimeclass_workloads/pod-number-cpu.yaml
index acbc89fce7..e17bd61ce9 100644
--- a/tests/integration/kubernetes/runtimeclass_workloads/pod-number-cpu.yaml
+++ b/tests/integration/kubernetes/runtimeclass_workloads/pod-number-cpu.yaml
@@ -16,6 +16,7 @@ spec:
     resources:
       limits:
         cpu: "500m"
+        memory: "128Mi"
   - name: c2
     image: quay.io/prometheus/busybox:latest
     command:
@@ -24,3 +25,4 @@ spec:
     resources:
       limits:
         cpu: "500m"
+        memory: "128Mi"
diff --git a/tests/integration/kubernetes/runtimeclass_workloads/pod-sandbox-vcpus-allocation.yaml b/tests/integration/kubernetes/runtimeclass_workloads/pod-sandbox-vcpus-allocation.yaml
index d5b1aaff6e..1ceb19973d 100644
--- a/tests/integration/kubernetes/runtimeclass_workloads/pod-sandbox-vcpus-allocation.yaml
+++ b/tests/integration/kubernetes/runtimeclass_workloads/pod-sandbox-vcpus-allocation.yaml
@@ -15,6 +15,9 @@ spec:
   containers:
   - name: vcpus-less-than-one-with-no-limits
     image: quay.io/prometheus/busybox:latest
+    resources:
+      limits:
+        memory: "128Mi"
     command: ['nproc', '--all']
   restartPolicy: Never
 ---
@@ -32,6 +35,7 @@ spec:
     resources:
       limits:
         cpu: "0.25"
+        memory: "128Mi"
     command: ['nproc', '--all']
   restartPolicy: Never
 ---
@@ -49,5 +53,6 @@ spec:
     resources:
       limits:
         cpu: "1.2"
+        memory: "128Mi"
     command: ['nproc', '--all']
   restartPolicy: Never
diff --git a/tests/integration/kubernetes/tests_common.sh b/tests/integration/kubernetes/tests_common.sh
index edc1ee09a7..f76566c07a 100644
--- a/tests/integration/kubernetes/tests_common.sh
+++ b/tests/integration/kubernetes/tests_common.sh
@@ -223,7 +223,7 @@ remove_kata_runtime_config_dropin_file() {
 }
 
 is_runtime_rs() {
-	[[ "${KATA_HYPERVISOR}" == *-runtime-rs ]]
+	[[ "${KATA_HYPERVISOR}" == *-runtime-rs ]] || [[ "${KATA_HYPERVISOR}" == "dragonball" ]]
 }
 
 # Copy the right combination of drop-ins from drop-in-examples/ into